Technology Category
Cognitive Modeling & Cognitive Systems: Neural Spike CodingMachine Learning: Deep Neural Architectures and Foundation ModelsNatural Language Processing: Speech
Artifact-free Sound Quality in DNN-based Closed-loop Systems for Audio Processing
🤖 AI Summary
Deep neural network (DNN)-based speech processing in hearing aids often introduces audible artifacts—such as distortion and noise—and suffers from low audio fidelity.
Method: This paper proposes dCoNNear, a closed-loop deep neural network architecture explicitly designed for auditory signal processing. It uniquely integrates biophysically grounded auditory models—representing both normal and impaired hearing—into a DNN-based closed-loop control framework. The system hierarchically emulates all non-DNN biological processing stages within personalized hearing aid algorithms, thereby eliminating sampling-mismatch-induced artifacts.
Contribution/Results: By embedding neurophysiologically plausible mechanisms, dCoNNear achieves zero audible artifacts while preserving modeling accuracy. Subjective listening evaluations demonstrate statistically significant improvements in audio quality ratings. This work establishes a novel paradigm for high-fidelity, clinically interpretable intelligent hearing assistance—bridging computational audiology and explainable AI.
Technology Category
Application Category
📝 Abstract
Recent advances in deep neural networks (DNNs) have significantly improved various audio processing applications, including speech enhancement, synthesis, and hearing aid algorithms. DNN-based closed-loop systems have gained popularity in these applications due to their robust performance and ability to adapt to diverse conditions. Despite their effectiveness, current DNN-based closed-loop systems often suffer from sound quality degradation caused by artifacts introduced by suboptimal sampling methods. To address this challenge, we introduce dCoNNear, a novel DNN architecture designed for seamless integration into closed-loop frameworks. This architecture specifically aims to prevent the generation of spurious artifacts. We demonstrate the effectiveness of dCoNNear through a proof-of-principle example within a closed-loop framework that employs biophysically realistic models of auditory processing for both normal and hearing-impaired profiles to design personalized hearing aid algorithms. Our results show that dCoNNear not only accurately simulates all processing stages of existing non-DNN biophysical models but also eliminates audible artifacts, thereby enhancing the sound quality of the resulting hearing aid algorithms. This study presents a novel, artifact-free closed-loop framework that improves the sound quality of audio processing systems, offering a promising solution for high-fidelity applications in audio and hearing technologies.
Problem
Research questions and friction points this paper is trying to address.
Sound Quality
Audio Processing
Assistive Technology
Innovation
Methods, ideas, or system contributions that make the work stand out.
dCoNNear
Deep Neural Network (DNN)
Audio Quality Enhancement
🔎 Similar Papers
No similar papers found.
